A2A MCP Server

An MCP server that implements an A2A Client for the A2A Protocol. The server can be used to connect and send messages to A2A Servers (remote agents).

The server needs to be initialised with one or more Agent Card URLs, each of which can have custom headers for authentication, configuration, etc.

Agents and their skills can be viewed with the list_available_agents tool, messages can be sent to the agents with the send_message_to_agent tool, and Artifacts that would overload the context can be viewed with view_text_artifact and view_data_artifact tools.

✨ Features

• Connect to any A2A Agent
• Use custom headers for authentication and configuration
• View Agent Cards and Skills
• Send messages to agents
• Continue conversations with agents
• View Artifacts that would overload the context
• Agent conversations are stored in JSON format

📋 Requirements

To run the server you need to install uv if you haven't already.

MacOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

🚀 Quick Start

1. Download Claude for Desktop
2. Add the below to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "a2a": {
      "command": "uvx",
      "args": ["a2anet-mcp"],
      "env": {
        "A2A_AGENT_CARDS": "[{"url": "https://example.com/.well-known/agent-card.json"}]"
      }
    }
  }
}

Tip: If you don't have an Agent Card URL, see: A2A Net Demo

⚙️ Configuration

A2A_AGENT_CARDS should be a JSON stringified list of objects. Each object must have a url key with the full path to the Agent Card. It can optionally have a custom_headers key with an object in the form {"header": "value"}:

export A2A_AGENT_CARDS='[
  {
    "url": "https://example.com/.well-known/agent-card.json",
    "custom_headers": {"X-API-Key": "your-key"} # Optional
  }
]'

🛠️ Tools

list_available_agents

Discover available agents and their capabilities.

send_message_to_agent

Send a message to an agent.

view_text_artifact

View text content from an artifact with optional line range selection.

view_data_artifact

View structured data from an artifact with optional filtering.

📖 Examples

List agents

list_available_agents({})

{
  "agents": [
    {
      "name": "Tweet Search",
      "description": "Find and analyze tweets by keyword, URL, author, list, or thread. Filter by language, media type, engagement, date range, or location. Get a clean table of tweets with authors, links, media, and counts; then refine the table and generate new columns with AI.",
      "skills": [
        {
          "name": "Search Tweets",
          "description": "Search X by keywords, URLs, handles, or conversation IDs. Filter by engagement (retweets/favorites/replies), dates, language, location, media type (images/videos/quotes), user verification status, and author/reply/mention relationships. Sort by Top or Latest. Return 1-10,000 results."
        },
        {
          "name": "View Table",
          "description": "View specific rows and columns from any table, ask questions about it, and analyse it with AI. If the agent performs searches, explain which rows are good and bad to improve the search."
        },
        {
          "name": "Filter Table",
          "description": "Filter any table with traditional filtering (i.e. patterns like names, URLs, etc). Explain what table you want to filter, and what rows you want to keep or remove."
        },
        {
          "name": "Filter Table with AI",
          "description": "Filter any table with AI filtering (i.e. reasoning, semantic understanding, etc). Explain what table you want to filter, and what rows you want to keep or remove."
        },
        {
          "name": "Generate Table",
          "description": "Generate a new table from any table with AI. Explain what table you want to generate from, what columns you want to keep, and what new columns you want to generate."
        }
      ],
      "url": "https://a2anet.com/agent/7TaFj4YlbpngypjX74zl/agent-card.json"
    }
  ],
  "count": 1,
  "tips": [
    "Use the agent name exactly as shown when calling send_message_to_agent",
    "Check the skills list to understand what each agent can do"
  ]
}

Send a message

send_message_to_agent({
  `message`: `Find tweets about AI from today (January 12, 2026)`,
  `agent_name`: `Tweet Search`
})

{
  "context_id": "cc9b9234-ecb7-4938-901a-a79912b8239f",
  "status": {
    "state": "completed",
    "message": {
      "parts": [
        {
          "type": "text",
          "text": "I found 10 tweets about "AI" posted on January 12, 2026. The search parameters used were:

- Search Terms: AI
- Start Date: 2026-01-12
- End Date: 2026-01-13
- Maximum Items: 10

Would you like to see more tweets, or do you want a summary or analysis of these results?"
        }
      ]
    }
  },
  "artifacts": [
    {
      "artifact_id": "97157147-db9f-490c-bc56-5603c99fd23b",
      "name": "AI Tweets from January 12, 2026",
      "description": "Tweets about AI posted on January 12, 2026.",
      "parts": [
        {
          "type": "data",
          "data": {
            "records": {
              "_total_rows": 10,
              "_columns": [
                {
                  "count": 1,
                  "unique_count": 1,
                  "types": [
                    {
                      "name": "int",
                      "count": 1,
                      "percentage": 100.0,
                      "sample_value": 213,
                      "minimum": 213,
                      "maximum": 213,
                      "average": 213
                    }
                  ],
                  "name": "quote.author.mediaCount"
                },
                ...,
                {
                  "count": 10,
                  "unique_count": 1,
                  "types": [
                    {
                      "name": "bool",
                      "count": 10,
                      "percentage": 100.0,
                      "sample_value": false
                    }
                  ],
                  "name": "isPinned"
                }
              ]
            },
            "_tip": "Object was minimized (original: 60,971 chars). String values truncated to 100 chars. Lists summarized. Use json_path to access specific fields, with rows/columns for list data."
          }
        }
      ]
    }
  ]
}

Multi-turn conversation

Use context_id to continue a conversation:

send_message_to_agent({
  `message`: `Can you summarize each of the 10 tweets in the table in 3-5 words each? Just give me a simple list with the author name and summary.`,
  `agent_name`: `Tweet Search`,
  `context_id`: `cc9b9234-ecb7-4938-901a-a79912b8239f`
})

{
  "context_id": "cc9b9234-ecb7-4938-901a-a79912b8239f",
  "status": {
    "state": "completed",
    "message": {
      "parts": [
        {
          "type": "text",
          "text": "Here is a simple list of each tweet's author and a 3-5 word summa

---